Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.5271. Min Act: -0.1700
Data Index: 3209794 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4488. Min Act: -0.1700
Data Index: 5933777 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4174. Min Act: -0.1700
Data Index: 6379933 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4018. Min Act: -0.1700
Data Index: 2802626 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4331. Min Act: -0.1700
Data Index: 6325270 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4018. Min Act: -0.1700
Data Index: 6503185 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3861. Min Act: -0.1700
Data Index: 3215213 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.4018. Min Act: -0.1700
Data Index: 2504494 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3704. Min Act: -0.1700
Data Index: 4257544 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3547. Min Act: -0.1700
Data Index: 3596517 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3547. Min Act: -0.1700
Data Index: 2067759 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3390. Min Act: -0.1700
Data Index: 5163702 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3547. Min Act: -0.1700
Data Index: 6241205 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3390. Min Act: -0.1700
Data Index: 8365618 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3233. Min Act: -0.1700
Data Index: 2476640 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3233. Min Act: -0.1700
Data Index: 6966857 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.3390. Min Act: -0.1700
Data Index: 4522148 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.2919. Min Act: -0.1700
Data Index: 6258279 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.2919. Min Act: -0.1700
Data Index: 5152104 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5271. Min Range: -3.5271
Max Act: 3.2762. Min Act: -0.1700
Data Index: 6897444 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19